Explainable AI

Policy summarization is a computational paradigm for explaining the behavior and decision-making processes of autonomous robots to humans. It summarizes robot policies via exemplary demonstrations, aiming to improve human understanding of robotic behaviors. This understanding is crucial, especially since users often make critical decisions about robot deployment in the real world. Previous research in policy summarization has predominantly focused on simulated robots and environments, overlooking its application to physically embodied robots. Our work fills this gap by combining current policy summarization methods with a novel, interactive user interface that involves physical interaction with robots. We conduct human-subject experiments to assess our explanation system, focusing on the impact of different explanation modalities in policy summarization. Our findings underscore the unique advantages of combining virtual and physical training environments to effectively communicate robot behavior to human users.

Effectively explaining decisions of black-box machine learning models is critical to responsible deployment of AI systems that rely on them. Recognizing their importance, the field of explainable AI (XAI) provides several techniques to generate these explanations. Yet, there is relatively little emphasis on the user (the explainee) in this growing body of work and most XAI techniques generate "one-size-fits-all" explanations. To bridge this gap and achieve a step closer towards human-centered XAI, we present I-CEE, a framework that provides Image Classification Explanations tailored to User Expertise. Informed by existing work, I-CEE explains the decisions of image classification models by providing the user with an informative subset of training data (i.e., example images), corresponding local explanations, and model decisions. However, unlike prior work, I-CEE models the informativeness of the example images to depend on user expertise, resulting in different examples for different users. We posit that by tailoring the example set to user expertise, I-CEE can better facilitate users’ understanding and simulatability of the model. To evaluate our approach, we conduct detailed experiments in both simulation and with human participants (N = 100) on multiple datasets. Experiments with simulated users show that I-CEE improves users’ ability to accurately predict the model’s decisions (simulatability) compared to baselines, providing promising preliminary results. Experiments with human participants demonstrate that our method significantly improves user simulatability accuracy, highlighting the importance of human-centered XAI.

Explainable AI (XAI) is widely viewed as a sine qua non for ever-expanding AI research. A better understanding of the needs of XAI users, as well as human-centered evaluations of explainable models are both a necessity and a challenge. In this paper, we explore how human-computer interaction (HCI) and AI researchers conduct user studies in XAI applications based on a systematic literature review. After identifying and thoroughly analyzing 97 core papers with human-based XAI evaluations over the past five years, we categorize them along the measured characteristics of explanatory methods, namely trust, understanding, usability , and human-AI collaboration performance . Our research shows that XAI is spreading more rapidly in certain application domains, such as recommender systems than in others, but that user evaluations are still rather sparse and incorporate hardly any insights from cognitive or social sciences. Based on a comprehensive discussion of best practices, i.e., common models, design choices, and measures in user studies, we propose practical guidelines on designing and conducting user studies for XAI researchers and practitioners. Lastly, this survey also highlights several open research directions, particularly linking psychological science and human-centered XAI.

Autonomous agents are increasingly being deployed amongst human end-users. Yet, human users often have little knowledge of how these agents work or what they will do next. This lack of transparency has already resulted in unintended consequences during AI use: a concerning trend which is projected to increase with the proliferation of autonomous agents. To curb this trend and ensure safe use of AI, assisting users in establishing an accurate understanding of agents that they work with is essential. In this work, we present AI teacher, a user-centered Explainable AI framework to address this need for autonomous agents that follow a Markovian policy. Our framework first computes salient instructions of agent behavior by estimating a user’s mental model and utilizing algorithms for sequential decision-making. Next, in contrast to existing solutions, these instructions are presented interactively to the end-users, thereby enabling a personalized approach to improving AI transparency. We evaluate our framework, with emphasis on its interactive features, through experiments with human participants. The experiment results suggest that, relative to non-interactive approaches, interactive teaching can both reduce the amount of time it takes for humans to create accurate mental models of these agents and is subjectively preferred by human users.

Existing research assessing human operators’ trust in automation and robots has primarily examined trust as a steady-state variable, with little emphasis on the evolution of trust over time. With the goal of addressing this research gap, we present a study exploring the dynamic nature of trust. We defined trust of entirety as a measure that accounts for trust across a human’s entire interactive experience with automation, and first identified alternatives to quantify it using real-time measurements of trust. Second, we provided a novel model that attempts to explain how trust of entirety evolves as a user interacts repeatedly with automation. Lastly, we investigated the effects of automation transparency on momentary changes of trust. Our results indicated that trust of entirety is better quantified by the average measure of "area under the trust curve" than the traditional post-experiment trust measure. In addition, we found that trust of entirety evolves and eventually stabilizes as an operator repeatedly interacts with a technology. Finally, we observed that a higher level of automation transparency may mitigate the "cry wolf" effect – wherein human operators begin to reject an automated system due to repeated false alarms.